© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 17520
    Prev
    Next
    INDEX
    Explanations

    acronyms related to degrees, certifications, and professional titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jenter
    -0.08
    é³
    -0.08
    èĮ
    -0.08
     pohod
    -0.07
    .tt
    -0.07
    acf
    -0.07
    afort
    -0.07
    Cog
    -0.07
    .xz
    -0.07
    anean
    -0.07
    POSITIVE LOGITS
    ()(
    0.06
    gnore
    0.06
     -
    0.06
     shed
    0.06
     vet
    0.06
    532
    0.05
     Planned
    0.05
    842
    0.05
     cum
    0.05
    ,
    0.05
    Activations Density 0.010%

    No Known Activations